Implementation notes: amd64, glyme, crypto_aead/hs1sivv2

Computer: glyme
Architecture: amd64
CPU ID: GenuineIntel-00020652-bfebfbff
SUPERCOP version: 201720170105
Operation: crypto_aead
Primitive: hs1sivv2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
14116	`faster`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
14116	`faster`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
14828	`dolbeau/amd64-sse`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
14828	`dolbeau/amd64-sse`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
15080	`faster`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
15084	`faster`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
15092	`faster`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
15092	`faster`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
15332	`faster`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170204	20170105
15344	`faster`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170204	20170105
15364	`faster`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170204	20170105
15520	`faster`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170204	20170105
15524	`faster`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170204	20170105
15532	`faster`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170204	20170105
15540	`faster`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170204	20170105
15588	`faster`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170204	20170105
15588	`faster`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170204	20170105
15696	`faster`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170204	20170105
15776	`faster`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170204	20170105
15824	`faster`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170204	20170105
15992	`faster`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170204	20170105
15996	`faster`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170204	20170105
15996	`faster`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170204	20170105
16184	`faster`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170204	20170105
16236	`faster`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170204	20170105
16292	`faster`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170204	20170105
16392	`dolbeau/amd64-sse`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170204	20170105
16392	`dolbeau/amd64-sse`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170204	20170105
16412	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170204	20170105
16416	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170204	20170105
16416	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170204	20170105
16420	`dolbeau/amd64-sse`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170204	20170105
16448	`faster`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
16456	`faster`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
16580	`dolbeau/amd64-sse`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170204	20170105
16620	`faster`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
16624	`faster`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
16644	`dolbeau/amd64-sse`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170204	20170105
16644	`dolbeau/amd64-sse`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170204	20170105
16656	`faster`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
16660	`faster`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20170204	20170105
16660	`faster`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20170204	20170105
16660	`faster`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
16660	`faster`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
16660	`faster`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
16660	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170204	20170105
16668	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170204	20170105
16680	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170204	20170105
16680	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170204	20170105
16680	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170204	20170105
16680	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170204	20170105
16692	`dolbeau/amd64-sse`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170204	20170105
16696	`faster`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
16704	`faster`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
16716	`faster`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
16720	`faster`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
16724	`faster`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
16724	`faster`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
16724	`faster`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
16732	`dolbeau/amd64-sse`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170204	20170105
16732	`dolbeau/amd64-sse`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170204	20170105
16748	`faster`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
16752	`faster`	`gcc -O3 -fomit-frame-pointer`	20170204	20170105
16756	`faster`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20170204	20170105
16756	`faster`	`gcc -m64 -O3 -fomit-frame-pointer`	20170204	20170105
16760	`faster`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20170204	20170105
16768	`faster`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20170204	20170105
16776	`faster`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20170204	20170105
16820	`faster`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20170204	20170105
16836	`faster`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
16840	`faster`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170204	20170105
16844	`faster`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
16912	`faster`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20170204	20170105
16924	`faster`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
16928	`faster`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
16936	`faster`	`gcc -O2 -fomit-frame-pointer`	20170204	20170105
16936	`faster`	`gcc -m64 -O2 -fomit-frame-pointer`	20170204	20170105
16952	`faster`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
16964	`faster`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170204	20170105
16972	`faster`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
16972	`faster`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170204	20170105
16996	`faster`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170204	20170105
17000	`faster`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170204	20170105
17004	`faster`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170204	20170105
17056	`faster`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
17072	`faster`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
17172	`faster`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
17180	`faster`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
17232	`faster`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
17248	`faster`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
17296	`faster`	`gcc -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
17304	`faster`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
17324	`faster`	`gcc -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
17340	`faster`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
17440	`faster`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20170204	20170105
17444	`faster`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20170204	20170105
17460	`faster`	`gcc -Os -fomit-frame-pointer`	20170204	20170105
17460	`faster`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20170204	20170105
17460	`faster`	`gcc -m64 -Os -fomit-frame-pointer`	20170204	20170105
17480	`faster`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20170204	20170105
17500	`faster`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20170204	20170105
17500	`faster`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20170204	20170105
17520	`faster`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
17532	`faster`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
17532	`faster`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
17536	`faster`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
17560	`faster`	`gcc -march=nocona -O -fomit-frame-pointer`	20170204	20170105
17564	`faster`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20170204	20170105
17572	`faster`	`gcc -funroll-loops -O -fomit-frame-pointer`	20170204	20170105
17572	`faster`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20170204	20170105
17576	`faster`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20170204	20170105
17608	`faster`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
17608	`faster`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
17644	`faster`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20170204	20170105
17648	`faster`	`gcc -O -fomit-frame-pointer`	20170204	20170105
17648	`faster`	`gcc -m64 -O -fomit-frame-pointer`	20170204	20170105
17720	`faster`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20170204	20170105
17736	`faster`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20170204	20170105
17860	`faster`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
17860	`faster`	`gcc -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
17960	`faster`	`gcc -march=k8 -O -fomit-frame-pointer`	20170204	20170105
17968	`faster`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20170204	20170105
19932	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170204	20170105
19932	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170204	20170105
19932	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170204	20170105
20216	`dolbeau/amd64-sse`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170204	20170105
20224	`dolbeau/amd64-sse`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170204	20170105
20224	`dolbeau/amd64-sse`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170204	20170105
37644	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
37664	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
38044	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
38044	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
38048	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
38072	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
38120	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
38320	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
38428	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20170204	20170105
38460	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20170204	20170105
38464	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20170204	20170105
39464	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
39492	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
39624	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
39624	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
40476	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
40516	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
40848	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
40860	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20170204	20170105
40868	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20170204	20170105
40876	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20170204	20170105
40948	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
41128	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
41132	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
41644	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170204	20170105
41648	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
41652	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
41740	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170204	20170105
41744	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170204	20170105
41764	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170204	20170105
41824	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170204	20170105
41952	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170204	20170105
44360	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20170204	20170105
44472	`ref`	`gcc -O3 -fomit-frame-pointer`	20170204	20170105
44520	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20170204	20170105
45048	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
45048	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
45060	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
45060	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
54132	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20170204	20170105
54148	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20170204	20170105
54176	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20170204	20170105
54612	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
54624	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
54816	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170204	20170105
54944	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20170204	20170105
54972	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20170204	20170105
55416	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
55704	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
55704	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
55744	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170204	20170105
55760	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170204	20170105
55772	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170204	20170105
55776	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170204	20170105
55808	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170204	20170105
55936	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
56452	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20170204	20170105
56540	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20170204	20170105
56732	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
57260	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
57316	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20170204	20170105
57336	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20170204	20170105
57552	`ref`	`gcc -O2 -fomit-frame-pointer`	20170204	20170105
66116	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20170204	20170105
66212	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20170204	20170105
66852	`faster`	`cc`	20170204	20170105
68860	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170204	20170105
68864	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170204	20170105
68868	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170204	20170105
68876	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170204	20170105
68892	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170204	20170105
68900	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170204	20170105
69176	`ref`	`gcc -O -fomit-frame-pointer`	20170204	20170105
69176	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20170204	20170105
69324	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20170204	20170105
69588	`ref`	`gcc -Os -fomit-frame-pointer`	20170204	20170105
69604	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20170204	20170105
69616	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20170204	20170105
69616	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
69616	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
69616	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
69628	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
69952	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
69968	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
69992	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20170204	20170105
70004	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
70016	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
70020	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20170204	20170105
70084	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
70100	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
70144	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20170204	20170105
70144	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20170204	20170105
70148	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20170204	20170105
70524	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
70952	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
71336	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
71448	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
71948	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170204	20170105
71948	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170204	20170105
71952	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170204	20170105
71972	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170204	20170105
71972	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170204	20170105
72428	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170204	20170105
81088	`faster`	`gcc`	20170204	20170105
81288	`faster`	`gcc -funroll-loops`	20170204	20170105
435348	`ref`	`gcc`	20170204	20170105
435764	`ref`	`gcc -funroll-loops`	20170204	20170105
474668	`ref`	`cc`	20170204	20170105

Compiler output

Implementation: crypto_aead/hs1sivv2/dolbeau/amd64-sse
Compiler: cc

encrypt.c: In file included from encrypt.c:190:
encrypt.c: ./c176.h:99:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'chacha_noxor176' that is compiled without support for 'ssse3'
encrypt.c: VEC4_QUARTERROUND( 0, 4, 8,12);
encrypt.c: ^
encrypt.c: ./c176.h:17:36: note: expanded from macro 'VEC4_QUARTERROUND'
encrypt.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
encrypt.c: ^
encrypt.c: ./c176.h:12:86: note: expanded from macro 'VEC4_QUARTERROUND_SHUFFLE'
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot16); \
encrypt.c: ^
encrypt.c: ./c176.h:99:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'chacha_noxor176' that is compiled without support for 'ssse3'
encrypt.c: ./c176.h:17:36: note: expanded from macro 'VEC4_QUARTERROUND'
encrypt.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
encrypt.c: ^
encrypt.c: ./c176.h:14:86: note: expanded from macro 'VEC4_QUARTERROUND_SHUFFLE'
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot8); \
encrypt.c: ^
encrypt.c: ./c176.h:100:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'chacha_noxor176' that is compiled without support for 'ssse3'
encrypt.c: VEC4_QUARTERROUND( 1, 5, 9,13);
encrypt.c: ^
encrypt.c: ./c176.h:17:36: note: expanded from macro 'VEC4_QUARTERROUND'
encrypt.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
encrypt.c: ^
encrypt.c: ./c176.h:12:86: note: expanded from macro 'VEC4_QUARTERROUND_SHUFFLE'
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot16); \
encrypt.c: ...

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
cc	dolbeau/amd64-sse
clang -O3 -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-sse
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-sse
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-sse
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-sse

Compiler output

Implementation: crypto_aead/hs1sivv2/dolbeau/amd64-avx2
Compiler: cc

encrypt.c: encrypt.c:90:2: error: "This code requires AVX2 to work"
encrypt.c: #error "This code requires AVX2 to work"
encrypt.c: ^
encrypt.c: 1 error generated.

Number of similar (compiler,implementation) pairs: 7, namely:

Compiler	Implementations
cc	dolbeau/amd64-avx2
clang -O3 -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-avx2
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-avx2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx2
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx2
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx2
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx2

Compiler output

Implementation: crypto_aead/hs1sivv2/dolbeau/amd64-avx512
Compiler: cc

encrypt.c: encrypt.c:90:2: error: "This code requires AVX512F to work"
encrypt.c: #error "This code requires AVX512F to work"
encrypt.c: ^
encrypt.c: encrypt.c:334:15: error: invalid input constraint 'Yz' in asm
encrypt.c: : [a] "Yz" (a)
encrypt.c: ^
encrypt.c: encrypt.c:482:26: warning: implicit declaration of function '_mm512_loadu_si512' is invalid in C99 [-Wimplicit-function-declaration]
encrypt.c: __m512i kv0 = _mm512_loadu_si512((const __m512i*)(nhkey+ 0)); // 1
encrypt.c: ^
encrypt.c: encrypt.c:482:19: error: initializing '__m512i' (vector of 8 'long long' values) with an expression of incompatible type 'int'
encrypt.c: __m512i kv0 = _mm512_loadu_si512((const __m512i*)(nhkey+ 0)); // 1
encrypt.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:483:19: error: initializing '__m512i' (vector of 8 'long long' values) with an expression of incompatible type 'int'
encrypt.c: __m512i kv4 = _mm512_loadu_si512((const __m512i*)(nhkey+ 4)); // 1
encrypt.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:484:19: error: initializing '__m512i' (vector of 8 'long long' values) with an expression of incompatible type 'int'
encrypt.c: __m512i kv8 = _mm512_loadu_si512((const __m512i*)(nhkey+ 8)); // 1, 2
encrypt.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:485:19: error: initializing '__m512i' (vector of 8 'long long' values) with an expression of incompatible type 'int'
encrypt.c: __m512i kv12 = _mm512_loadu_si512((const __m512i*)(nhkey+12)); // 1, 2
encrypt.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:486:19: error: initializing '__m512i' (vector of 8 'long long' values) with an expression of incompatible type 'int'
encrypt.c: __m512i kv16 = _mm512_loadu_si512((const __m512i*)(nhkey+16)); // 2
encrypt.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:487:19: error: initializing '__m512i' (vector of 8 'long long' values) with an expression of incompatible type 'int'
encrypt.c: ...

Number of similar (compiler,implementation) pairs: 7, namely:

Compiler	Implementations
cc	dolbeau/amd64-avx512
clang -O3 -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-avx512
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-avx512
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx512
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx512
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx512
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx512

Compiler output

Implementation: crypto_aead/hs1sivv2/dolbeau/amd64-sse
Compiler: gcc

Number of similar (compiler,implementation) pairs: 70, namely:

Compiler	Implementations
gcc	dolbeau/amd64-sse
gcc -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops	dolbeau/amd64-sse
gcc -funroll-loops -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-sse

Compiler output

Implementation: crypto_aead/hs1sivv2/dolbeau/amd64-avx2
Compiler: gcc

Number of similar (compiler,implementation) pairs: 93, namely:

Compiler	Implementations
gcc	dolbeau/amd64-avx2
gcc -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops	dolbeau/amd64-avx2
gcc -funroll-loops -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx2
gcc -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx2

Compiler output

Implementation: crypto_aead/hs1sivv2/dolbeau/amd64-avx512
Compiler: gcc

Number of similar (compiler,implementation) pairs: 2, namely:

Compiler	Implementations
gcc	dolbeau/amd64-avx512
gcc -funroll-loops	dolbeau/amd64-avx512

Compiler output

Implementation: crypto_aead/hs1sivv2/dolbeau/amd64-avx512
Compiler: gcc -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 92, namely:

Compiler	Implementations
gcc -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=corei7 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx512
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx512
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx512
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx512
gcc -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx512

Compiler output

Implementation: crypto_aead/hs1sivv2/dolbeau/amd64-sse
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

encrypt.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: c176.h: In function 'chacha_noxor176':
encrypt.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:190:0:
encrypt.c: c176.h:14:84: note: called from here
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot8); \
encrypt.c: ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: c176.h:17:36: note: in expansion of macro 'VEC4_QUARTERROUND_SHUFFLE'
encrypt.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: c176.h:106:7: note: in expansion of macro 'VEC4_QUARTERROUND'
encrypt.c: VEC4_QUARTERROUND( 3, 4, 9,14);
encrypt.c: ^~~~~~~~~~~~~~~~~
encrypt.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:190:0:
encrypt.c: c176.h:12:84: note: called from here
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot16); \
encrypt.c: ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: ...
encrypt.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: c176.h: In function 'chacha_noxor176':
encrypt.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:190:0:
encrypt.c: c176.h:14:84: note: called from here
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot8); \
encrypt.c: ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: c176.h:17:36: note: in expansion of macro 'VEC4_QUARTERROUND_SHUFFLE'
encrypt.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: c176.h:106:7: note: in expansion of macro 'VEC4_QUARTERROUND'
encrypt.c: VEC4_QUARTERROUND( 3, 4, 9,14);
encrypt.c: ^~~~~~~~~~~~~~~~~
encrypt.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:190:0:
encrypt.c: c176.h:12:84: note: called from here
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot16); \
encrypt.c: ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-sse

Compiler output

Implementation: crypto_aead/hs1sivv2/dolbeau/amd64-avx2
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

encrypt.c: encrypt.c:90:2: error: #error "This code requires AVX2 to work"
encrypt.c: #error "This code requires AVX2 to work"
encrypt.c: ^~~~~
encrypt.c: encrypt.c: In function 'prf_hash2_2':
encrypt.c: encrypt.c:425:19: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i kv0 = _mm256_loadu_si256((const __m256i*)(nhkey+ 0)); // 1
encrypt.c: ^~~
encrypt.c: encrypt.c:90:2: error: #error "This code requires AVX2 to work"
encrypt.c: #error "This code requires AVX2 to work"
encrypt.c: ^~~~~
encrypt.c: encrypt.c: In function 'prf_hash2_2':
encrypt.c: encrypt.c:425:19: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i kv0 = _mm256_loadu_si256((const __m256i*)(nhkey+ 0)); // 1
encrypt.c: ^~~

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx2

Compiler output

Implementation: crypto_aead/hs1sivv2/dolbeau/amd64-avx512
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

encrypt.c: encrypt.c:90:2: error: #error "This code requires AVX512F to work"
encrypt.c: #error "This code requires AVX512F to work"
encrypt.c: ^~~~~
encrypt.c: encrypt.c: In function '_mm512_reduce_add_epi64':
encrypt.c: encrypt.c:321:20: note: The ABI for passing parameters with 64-byte alignment has changed in GCC 4.6
encrypt.c: unsigned long long _mm512_reduce_add_epi64 (__m512i a) {
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c: In function 'prf_hash2_2':
encrypt.c: encrypt.c:482:19: warning: AVX512F vector return without AVX512F enabled changes the ABI [-Wpsabi]
encrypt.c: __m512i kv0 = _mm512_loadu_si512((const __m512i*)(nhkey+ 0)); // 1
encrypt.c: ^~~
encrypt.c: encrypt.c:501:19: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i inv0 = _mm256_inserti128_si256(_mm256_castsi128_si256(inv0lo), inv0lo, 1);
encrypt.c: ^~~~
encrypt.c: encrypt.c:90:2: error: #error "This code requires AVX512F to work"
encrypt.c: #error "This code requires AVX512F to work"
encrypt.c: ^~~~~
encrypt.c: encrypt.c: In function '_mm512_reduce_add_epi64':
encrypt.c: encrypt.c:321:20: note: The ABI for passing parameters with 64-byte alignment has changed in GCC 4.6
encrypt.c: unsigned long long _mm512_reduce_add_epi64 (__m512i a) {
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c: In function 'prf_hash2_2':
encrypt.c: encrypt.c:482:19: warning: AVX512F vector return without AVX512F enabled changes the ABI [-Wpsabi]
encrypt.c: __m512i kv0 = _mm512_loadu_si512((const __m512i*)(nhkey+ 0)); // 1
encrypt.c: ^~~
encrypt.c: encrypt.c:501:19: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i inv0 = _mm256_inserti128_si256(_mm256_castsi128_si256(inv0lo), inv0lo, 1);
encrypt.c: ^~~~

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx512

Compiler output

Implementation: crypto_aead/hs1sivv2/dolbeau/amd64-avx2
Compiler: gcc -m64 -march=core2 -O2 -fomit-frame-pointer

encrypt.c: encrypt.c:90:2: error: #error "This code requires AVX2 to work"
encrypt.c: #error "This code requires AVX2 to work"
encrypt.c: ^~~~~
encrypt.c: encrypt.c: In function 'chacha_noxor176':
encrypt.c: encrypt.c:194:18: fatal error: c176.h: No such file or directory
encrypt.c: #include "c176.h"
encrypt.c: ^
encrypt.c: compilation terminated.

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2